org.languagetool.rules.de.DashRule.java Source code

Introduction

Here is the source code for org.languagetool.rules.de.DashRule.java

Source

/* LanguageTool, a natural language style checker 
 * Copyright (C) 2005 Daniel Naber (http://www.danielnaber.de)
 * 
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
 * USA
 */
package org.languagetool.rules.de;

import java.util.*;

import org.apache.commons.lang3.StringUtils;
import org.languagetool.AnalyzedSentence;
import org.languagetool.AnalyzedTokenReadings;
import org.languagetool.rules.*;

/**
 * Prft, dass in Bindestrich-Komposita kein Leerzeichen eingefgt wird (wie z.B. in 'Diten- Erhhung').
 *   
 * @author Daniel Naber
 */
public class DashRule extends Rule {

    public DashRule(ResourceBundle messages) {
        super.setCategory(Categories.COMPOUNDING.getCategory(messages));
        addExamplePair(Example.wrong("Bundestag beschliet <marker>Diten- Erhhung</marker>"),
                Example.fixed("Bundestag beschliet <marker>Diten-Erhhung</marker>"));
    }

    @Override
    public String getId() {
        return "DE_DASH";
    }

    @Override
    public String getDescription() {
        return "Keine Leerzeichen in Bindestrich-Komposita (wie z.B. in 'Diten- Erhhung')";
    }

    @Override
    public RuleMatch[] match(AnalyzedSentence sentence) {
        List<RuleMatch> ruleMatches = new ArrayList<>();
        AnalyzedTokenReadings[] tokens = sentence.getTokensWithoutWhitespace();
        String prevToken = null;
        for (int i = 0; i < tokens.length; i++) {
            String token = tokens[i].getToken();
            if (prevToken != null && prevToken.endsWith("-") && !prevToken.equals("-") && !prevToken.contains("--")
                    && !prevToken.contains("-") // first char is some special kind of dash, found in Wikipedia
            ) {
                char firstChar = token.charAt(0);
                if (Character.isUpperCase(firstChar)) {
                    if (!StringUtils.equalsAny(token, "UND", "ODER", "BZW")) { // ignore "NORD- UND SDKOREA"
                        String msg = "Mglicherweise fehlt ein 'und' oder ein Komma, oder es wurde nach dem Wort "
                                + "ein berflssiges Leerzeichen eingefgt. Eventuell haben Sie auch versehentlich einen Bindestrich statt eines Punktes eingefgt.";
                        String shortMsg = "Fehlendes 'und' oder Komma oder berflssiges Leerzeichen?";
                        int fromPos = tokens[i - 1].getStartPos();
                        RuleMatch ruleMatch = new RuleMatch(this, sentence, fromPos,
                                fromPos + prevToken.length() + 1, msg, shortMsg);
                        String prevTokenStr = tokens[i - 1].getToken();
                        ruleMatch.setSuggestedReplacements(Arrays.asList(prevTokenStr, prevTokenStr + ", "));
                        ruleMatches.add(ruleMatch);
                    }
                }
            }
            prevToken = token;
        }
        return toRuleMatchArray(ruleMatches);
    }

}